Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registration (2203.13239v1)

Published 24 Mar 2022 in cs.CV

Abstract: 3D point cloud registration in remote sensing field has been greatly advanced by deep learning based methods, where the rigid transformation is either directly regressed from the two point clouds (correspondences-free approaches) or computed from the learned correspondences (correspondences-based approaches). Existing correspondences-free methods generally learn the holistic representation of the entire point cloud, which is fragile for partial and noisy point clouds. In this paper, we propose a correspondences-free unsupervised point cloud registration (UPCR) method from the representation separation perspective. First, we model the input point cloud as a combination of pose-invariant representation and pose-related representation. Second, the pose-related representation is used to learn the relative pose wrt a "latent canonical shape" for the source and target point clouds respectively. Third, the rigid transformation is obtained from the above two learned relative poses. Our method not only filters out the disturbance in pose-invariant representation but also is robust to partial-to-partial point clouds or noise. Experiments on benchmark datasets demonstrate that our unsupervised method achieves comparable if not better performance than state-of-the-art supervised registration methods.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Zhiyuan Zhang (129 papers)
  2. Jiadai Sun (16 papers)
  3. Yuchao Dai (123 papers)
  4. Dingfu Zhou (24 papers)
  5. Xibin Song (24 papers)
  6. Mingyi He (27 papers)
Citations (12)

Summary

We haven't generated a summary for this paper yet.